A speech recognition grammar creating apparatus, which is capable of eliminating complex labor associated with preparing all rules by taking into account changes of the order of component elements of a speech-recognizing object and possible combinations of component elements including at least one component element that can be omitted. In the speech recognition grammar creating apparatus, an image edit section groups together at least one component element that cannot be omitted and at least one component element that can be omitted, as the speech-recognizing object, into a component element group as an omission-allowed group. An augmented BNF converting section creates the speech recognition grammar by expanding the component element group obtained by the grouping.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A speech recognition grammar creating apparatus that describes a speech-recognizing object as a speech recognition grammar, comprising: a grouping unit adapted to create a component group of n component elements, wherein n is an integer not less than 2; a first determination unit adapted to determine if the component group of n component elements is a group including at least one component element that cannot be omitted; a second determination unit adapted to determine if the n component elements are order designated when it is determined by said first determination unit that the component group is the group including the at least one component element that cannot be omitted; and a creating unit adapted to create the speech recognition grammar by creating sequences of the n component elements and combinations thereof according to the designated order when it is determined by said second determination unit that the n component elements are order designated, and by creating respective permutations of the n component elements and combinations thereof when it is determined by said second determination unit that the n component elements are not order designated.
2. A speech recognition grammar creating apparatus as claimed in claim 1 , further comprising a display device that displays the sequences of the n component elements and combinations thereof and and the permutations of the n component elements and combinations thereof created by said creating device.
3. A speech recognition grammar creating apparatus as claimed in claim 2 , wherein said display device is a graphic display device.
4. A speech recognition grammar creating apparatus as claimed in claim 2 , further comprising an input section, wherein said display device displays an editing work process of operations in response to input data entered by a user in response to contents presented on said display device.
5. A speech recognition grammar creating apparatus as claimed in claim 1 , wherein said creating device creates the speech recognition grammar in a metalanguage format.
6. A speech recognition grammar creating apparatus as claimed in claim 5 , wherein the metalanguage format is augmented BNF (Augmented Backus Naur Form).
7. A speech recognition grammar creating apparatus as claimed in claim 1 , wherein said creating device creates the speech recognition grammar in a transition network format.
8. A speech recognition grammar creating apparatus as claimed in claim 7 , wherein the transition network format is a format in which a combination of component elements is expressed by a network that indicates connections between component elements formed by connecting combinable component elements by arrows.
9. A computer-readable storage medium encoded with computer executable instructions that cause a computer to execute a control method for a speech recognition grammar creating apparatus that describes a speech-recognizing object as a speech recognition grammar, the method comprising: creating a component group of n component elements, wherein n is an integer not less than 2; determining if the component group on n component elements is a group including at least one component element that cannot be omitted; determining if the n components elements are order designated when it is determined by said first determination unit that the component group is the group including the at least one component element that cannot be omitted; and creating the speech recognition grammar by creating sequences of the n component elements and combinations thereof according to the designated order when it is determined by said second determination unit that the n components elements are order designated, and by creating respective permutations of the n component elements and combinations thereof when it is determined by said second determination unit that the n components elements are not order designated.
10. A control method for a speech recognition grammar creating apparatus that describes a speech-recognizing object as a speech recognition grammar, comprising: creating a component group of n component elements, wherein n is an integer not less than 2; determining if the component group on n component elements is a group including at least one component element that cannot be omitted; determining if the n component elements are order designated when it is determined by said first determination unit that the component group is the group including the at least one component element that cannot be omitted; and creating the speech recognition grammar by creating sequences of the n component elements and combinations thereof according to the designated order when it is determined by said second determination unit that the n component elements are order designated, and by creating respective permutations of the n component elements and combinations thereof when it is determined by said second determination unit that the n component elements are not order designated.
11. A control method as claimed in claim 10 , further comprising displaying the sequences of the n component elements and combinations thereof and the permutations of the n component elements and combinations thereof on a display device.
12. A control method as claimed in claim 10 , wherein the speech recognition grammar is created in a metalanguage format.
13. A control method as claimed in claim 12 , wherein the metalanguage format is augmented BNF (Augmented Backus Naur Form).
14. A control method as claimed in claim 10 , wherein the speech recognition grammar is created in a transition network format.
15. A control method as claimed in claim 14 , wherein the transition network format is a format in which a combination of component elements is expressed by a network that indicates connections between component elements formed by connecting combinable component elements by arrows.
16. A control method as claimed in claim 11 , wherein said display device displays an editing work process of operations in response to input data entered by a user via an input device in response to contents presented on said display device.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 29, 2005
October 13, 2009
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.